Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    >The
    -0.07
     hears
    -0.07
     sıra
    -0.07
    strument
    -0.07
     Addresses
    -0.06
     inference
    -0.06
     auditor
    -0.06
     spectral
    -0.06
    527
    -0.06
    jandro
    -0.06
    POSITIVE LOGITS
     Rig
    0.07
    تغ
    0.07
    ivia
    0.07
    燃
    0.06
    VB
    0.06
     změ
    0.06
    輔
    0.06
    Apps
    0.06
    041
    0.06
    =>$
    0.05
    Act Density 0.047%

    No Known Activations